© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90986
    Prev
    Next
    INDEX
    Explanations

    adding context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     abstrait
    -0.46
     circonstances
    -0.45
     deberes
    -0.45
     venons
    -0.44
    ⓧ
    -0.43
     없습니다
    -0.43
     esquem
    -0.42
    León
    -0.42
    Viki
    -0.41
    originally
    -0.41
    POSITIVE LOGITS
    stateProvider
    0.68
    fromnode
    0.65
     AssemblyCulture
    0.61
    Datuak
    0.60
     practicing
    0.56
     throughout
    0.56
     consultato
    0.54
     препратки
    0.54
    DockStyle
    0.54
     الرياضيه
    0.54
    Activations Density 0.008%

    No Known Activations